Related papers: Protocol Dialects as Formal Patterns: A Composable…

Humans continuously adapt their style and language to a variety of domains. However, a reliable definition of `domain' has eluded researchers thus far. Additionally, the notion of discrete domains stands in contrast to the multiplicity of…

We propose an entanglement-based protocol for two people to simultaneously exchange their messages. We show that the protocol is asymptotically secure against the disturbance attack, the intercept-and-resend attack and the…

As state-of-the-art Large Language Models (LLMs) have become ubiquitous, ensuring equitable performance across diverse demographics is critical. However, it remains unclear whether these disparities arise from the explicitly stated identity…

Audio CAPTCHAs are supposed to provide a strong defense for online resources; however, advances in speech-to-text mechanisms have rendered these defenses ineffective. Audio CAPTCHAs cannot simply be abandoned, as they are specifically named…

We investigate the processing of idiomatic expressions in transformer-based language models using a novel set of techniques for circuit discovery and analysis. First discovering circuits via a modified path patching algorithm, we find that…

Failure detection protocols---a fundamental building block for crafting fault-tolerant distributed systems---are in many cases described by their authors making use of informal pseudo-codes of their conception. Often these pseudo-codes use…

With the rapid development of technology and the acceleration of digitalisation, the frequency and complexity of cyber security threats are increasing. Traditional cybersecurity approaches, often based on static rules and predefined…

Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat modelling, prior work has primarily evaluated a number of general-purpose Large Language Models…

Abstracting Gradual Typing (AGT) is an approach to systematically deriving gradual counterparts to static type disciplines. The approach consists of defining the semantics of gradual types by interpreting them as sets of static types, and…

Large multilingual language models typically share their parameters across all languages, which enables cross-lingual task transfer, but learning can also be hindered when training updates from different languages are in conflict. In this…

Most of the world's languages and dialects are low-resource, and lack support in mainstream machine translation (MT) models. However, many of them have a closely-related high-resource language (HRL) neighbor, and differ in linguistically…

Building NLP systems that serve everyone requires accounting for dialect differences. But dialects are not monolithic entities: rather, distinctions between and within dialects are captured by the presence, absence, and frequency of dozens…

There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators ("LLM-as-a-judge") is a growing research area, their sensitivity to dialectal…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Password security hinges on an in-depth understanding of the techniques adopted by attackers. Unfortunately, real-world adversaries resort to pragmatic guessing strategies such as dictionary attacks that are inherently difficult to model in…

Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In…

Assessing ways in which Language Models can reduce their hallucinations and improve the outputs' quality is crucial to ensure their large-scale use. However, methods such as fine-tuning on domain-specific data or the training of a separate…

Internet of Things (IoT) have gained popularity in recent times. With an increase in the number of IoT devices, security and privacy vulnerabilities are also increasing. For sensitive domains like healthcare and industrial sectors, such…

Generating logical form equivalents of human language is a fresh way to employ neural architectures where long short-term memory effectively captures dependencies in both encoder and decoder units. The logical form of the sequence usually…